Auto-activating smart responses based on activities from remote devices

CROSS-REFERENCE TO RELATED APPLICATION

This application is a continuation of U.S. Ser. No. 14/450,726, filed on Aug. 4, 2014, entitled AUTO-ACTIVATING SMART RESPONSES BASED ON ACTIVITIES FROM REMOTE DEVICES, which claims priority from U.S. Provisional Ser. No. 61/862,927, filed on Aug. 6, 2013, entitled AUTO-ACTIVATING SMART RESPONSES BASED ON ACTIVITIES FROM REMOTE DEVICES, both of which are hereby incorporated by reference in their entirety for all purposes.

BACKGROUND

The disclosed embodiments relate generally to digital assistant systems, and more specifically, to automatically responding to incoming communications.

Just like human personal assistants, digital assistant systems can perform requested tasks and provide requested advice, information, or services. A digital assistant system's ability to fulfill a user's request is dependent on the digital assistant system's correct comprehension of the request or instructions. Recent advances in natural language processing have enabled users to interact with digital assistant systems using natural language, in spoken or textual forms. Such digital assistant systems can interpret the user's input to infer the user's intent, translate the inferred intent into actionable tasks and parameters, execute operations or deploy services to perform the tasks, and produce output that is intelligible to the user. Ideally, the output produced by a digital assistant system should fulfill the user's intent expressed during the natural language interaction between the user and the digital assistant system.

The ability of a digital assistant system to produce satisfactory responses to user requests depends on the natural language processing, knowledge base, and artificial intelligence available to the digital assistant system. Moreover, while numerous third party systems and services currently exist, there is no efficient means for a digital assistant system to automatically perform a specified action in response to reception of an incoming communication from one or more specified senders.

SUMMARY

The embodiments disclosed herein provide methods, devices, systems, and non-transitory computer readable storage media for operating a digital assistant so as to automatically perform a specified action in response to reception of an incoming communication from one or more specified senders.

Some embodiments provide a method of causing a digital assistant to automatically respond to incoming communications. The method is performed at one or more electronic devices that each include one or more processors and memory. First, a speech input is obtained from a user. In response to obtaining the speech input, it is determined whether the speech input includes instructions for performing a specified action in response to receipt of a subsequent incoming communication from one or more specified senders. Thereafter, instructions the instructions are stored. After storing the instructions, an incoming communication is obtained from a respective sender. It is determined whether the respective sender is one of the one or more specified senders. Upon determining that the respective sender is one of the one or more specified senders, the specified action is performed in accordance with the instructions. Thereafter, the instructions are automatically (i.e., without human intervention) deleted.

In some embodiments, determining whether the speech input includes instructions includes determining whether the speech input includes instructions for performing the specified action in response to receipt of one or more specified subsequent incoming communication types from one or more specified senders. Upon determining that the respective sender is one of the one or more specified senders and that the incoming communication is one of the one or more specified subsequent incoming communication types, the specified action is performed in accordance with the instructions. Thereafter, the instructions are automatically (i.e., without human intervention) deleted.

In some embodiments, a respective specified subsequent incoming communication type of the one or more specified subsequent incoming communication types is one of a phone call, voice message, voicemail, video call, SMS, MMS, VOIP call, or email.

In some embodiments, the incoming communication is a phone call, and where the specified action is sending a voice message.

In some embodiments, at least a part of the voice message is a recording of the user's voice.

In some embodiments, at least a part of the voice message is a digitized or text-to-speech version of input text.

In some embodiments, the method includes performing natural language processing on the speech input so as to convert the speech input into text, and where storing the instructions includes storing the instructions as text.

In some embodiments, performing the specified action includes: composing a response to the respective sender in accordance with the instructions; and communicating the response to the sender.

In some embodiments, the communicating is one of a phone call, voicemail, video call, SMS, MMS, VOIP call, or email.

In some embodiments, the communicating uses the same means of communication as the incoming communication.

In some embodiments, the composing includes composing the response to the respective sender in accordance with the instructions and based at least in part on contextual information.

In some embodiments, the contextual information includes one or more of location information, pattern information, or behavior information associated with the user.

In some embodiments, determining whether the respective sender is one of the one or more specified senders includes ascertaining whether the respective sender is one of the one or more specified senders based on a list of contacts associated with the user of the device.

In some embodiments, determining whether the respective sender is one of the one or more specified senders includes ascertaining whether the respective sender is one of the one or more specified senders based on caller ID associated with the respective sender.

In some embodiments, the method includes identifying an address associated with the sender of the communication, and determining whether the respective sender is one of the one or more specified senders includes ascertaining whether the sender is one of the one or more specified senders based on the address associated with the respective sender of the communication.

In some embodiments, determining whether the respective sender is one of the one or more specified senders includes ascertaining whether the sender is one of the one or more specified senders based on the content of the incoming communication received from the respective sender.

In some embodiments, the specified subsequent incoming communication type is one of a phone call, voice message, voicemail, video call, SMS, MMS, VOIP call, or email.

In some embodiments, the incoming communication is one of a phone call, voice message, voicemail, video call, SMS, MMS, VOIP call, or email.

In some embodiments, the action is selected from the group consisting of: sending a voice message to the sender; sending an SMS message to the sender; sending an MMS or photograph to the sender; sending an email to the sender; sending an event invite to the sender; sharing one or more calendar entries with the sender; and sharing one or more custom attributes with the sender.

In some embodiments, the performing and deleting are automatically performed without further review or instruction from the user of the device.

In some embodiments, performing the specified action includes: performing a first sub-action; and performing a second sub-action different from the first sub-action.

In some embodiments, the instructions further specify an expiration period; and the method including, upon determining that the respective sender is not one of the one or more specified senders and that the expiration period has elapsed, automatically deleting the instructions.

In some embodiments, the respective sender is a first respective sender; and the method includes: upon determining that the first respective sender is not one of the one or more specified senders and the expiration period has not elapsed, forgoing deletion of the instructions; obtaining an incoming communication from a second respective sender different from the first respective sender; determining whether the second respective sender is one of the one or more specified senders; and upon determining that the second respective sender is one of the one or more specified senders and that the expiration period has not elapsed, performing the specified action in accordance with the instructions and thereafter automatically deleting the instructions.

In accordance with some embodiments, a non-transitory computer readable storage medium has stored therein instructions, which, when executed by an electronic device with one or more processors, cause the device to perform the operations of any of the methods described above. In accordance with some embodiments, an electronic device includes one or more processors, memory, and one or more programs; the one or more programs are stored in the memory and configured to be executed by the one or more processors and the one or more programs include instructions for performing the operations of any of the methods described above. In accordance with some embodiments, a graphical user interface on an electronic device with a display, a memory, and one or more processors to execute one or more programs stored in the memory, the graphical user interface comprising user interfaces displayed in accordance with any of the methods described above. In accordance with some embodiments, an electronic device includes means for performing the operations of any of the methods described above. In accordance with some embodiments, an information processing apparatus, for use in an electronic device includes means for performing the operations of any of the methods described above.

In accordance with some embodiments, an electronic device includes a sound receiving unit configured to obtain a speech input from a user. The electronic device also includes a processing unit coupled to the sound receiving unit. In response to obtaining the speech input, the processing unit is configured to determine whether the speech input includes instructions for performing a specified action in response to receipt of a subsequent incoming communication from one or more specified senders and instruction from the first user. Thereafter, the processing unit is configured to store the instructions. After storing the instructions, the processing unit is configured to obtain an incoming communication from a respective sender. Thereafter, the processing unit is configured to determine whether the respective sender is one of the one or more specified senders. Upon determining that the respective sender is one of the one or more specified senders, the processing unit is configured to perform the specified action in accordance with the instructions. Thereafter, the processing unit is configured to automatically delete the instructions.

The details of one or more embodiments of the subject matter described in this specification are set forth in the accompanying drawings and the description below. Other features, aspects, and advantages of the subject matter will become apparent from the description, the drawings, and the claims.

BRIEF DESCRIPTION OF THE DRAWINGS

<figref idref="DRAWINGS">FIG. <b>1</b></figref> is a block diagram illustrating an environment in which a digital assistant operates in accordance with some embodiments.

<figref idref="DRAWINGS">FIG. <b>2</b></figref> is a block diagram illustrating a digital assistant client system in accordance with some embodiments.

<figref idref="DRAWINGS">FIG. <b>3</b>A</figref> is a block diagram illustrating a digital assistant system or a server portion thereof in accordance with some embodiments.

<figref idref="DRAWINGS">FIG. <b>3</b>B</figref> is a block diagram illustrating functions of the digital assistant shown in <figref idref="DRAWINGS">FIG. <b>3</b>A</figref> in accordance with some embodiments.

<figref idref="DRAWINGS">FIG. <b>3</b>C</figref> is a diagram of a portion of an ontology shown in <figref idref="DRAWINGS">FIG. <b>3</b>B</figref> in accordance with some embodiments.

<figref idref="DRAWINGS">FIG. <b>4</b></figref> is a diagram of a portion of an ontology for automatically performing a specified action in response to reception of an incoming communication from one of the one or more specified senders in accordance with some embodiments.

<figref idref="DRAWINGS">FIG. <b>5</b></figref> illustrates a flow diagram for an exemplary process of operating a digital assistant in accordance with some embodiments.

<figref idref="DRAWINGS">FIG. <b>6</b></figref> illustrates a flow diagram for an exemplary process of operating a digital assistant in accordance with some embodiments.

<figref idref="DRAWINGS">FIG. <b>7</b></figref> is a functional block diagram of an electronic device in accordance with some embodiments.

Like reference numerals refer to corresponding parts throughout the drawings.

DESCRIPTION OF EMBODIMENTS

<figref idref="DRAWINGS">FIG. <b>1</b></figref> is a block diagram of an operating environment <b>100</b> of a digital assistant according to some embodiments. The terms “digital assistant,” “virtual assistant,” “intelligent automated assistant,” or “automatic digital assistant,” refer to any information processing system that interprets natural language input in spoken and/or textual form to infer user intent, and performs actions based on the inferred user intent. For example, to act on an inferred user intent, the system can perform one or more of the following: identifying a task flow with steps and parameters designed to accomplish the inferred user intent; inputting specific requirements from the inferred user intent into the task flow; executing the task flow by invoking programs, methods, services, APIs, or the like; and generating output responses to the user in an audible (e.g., speech) and/or visual form.

Specifically, a digital assistant (DA) is capable of accepting a user request at least partially in the form of a natural language command, request, statement, narrative, and/or inquiry. Typically, the user request seeks either an informational answer or performance of a task by the digital assistant. A satisfactory response to the user request is either provision of the requested informational answer, performance of the requested task, or a combination of the two. For example, a user may ask the digital assistant a question, such as “Where am I right now?” Based on the user's current location, the digital assistant may answer, “You are in Central Park.” The user may also request the performance of a task, for example, “Please remind me to call Mom at 4 PM today.” In response, the digital assistant may acknowledge the request and then create an appropriate reminder item in the user's electronic schedule. During performance of a requested task, the digital assistant sometimes interacts with the user in a continuous dialogue involving multiple exchanges of information over an extended period of time. There are numerous other ways of interacting with a digital assistant to request information or performance of various tasks. In addition to providing verbal responses and taking programmed actions, the digital assistant also provides responses in other visual or audio forms (e.g., as text, alerts, music, videos, animations, etc.).

An example of a digital assistant is described in Applicant's U.S. Utility application Ser. No. 12/987,982 for “Intelligent Automated Assistant,” filed Jan. 10, 2011, the entire disclosure of which is incorporated herein by reference.

As shown in <figref idref="DRAWINGS">FIG. <b>1</b></figref>, in some embodiments, a digital assistant is implemented according to a client-server model. The digital assistant includes a client-side portion <b>102</b><i>a</i>, <b>102</b><i>b </i>(hereinafter “DA-client <b>102</b>”) executed on a user device <b>104</b><i>a</i>, <b>104</b><i>b</i>, and a server-side portion <b>106</b> (hereinafter “DA-server <b>106</b>”) executed on a server system <b>108</b>. DA-client <b>102</b> communicates with DA-server <b>106</b> through one or more networks <b>110</b>. DA-client <b>102</b> provides client-side functionalities such as user-facing input and output processing and communications with DA-server <b>106</b>. DA-server <b>106</b> provides server-side functionalities for any number of DA-clients <b>102</b> each residing on a respective user device <b>104</b>.

In some embodiments, DA-server <b>106</b> includes a client-facing I/O interface <b>112</b>, one or more processing modules <b>114</b>, data and models <b>116</b>, and an I/O interface to external services <b>118</b>. The client-facing I/O interface facilitates the client-facing input and output processing for digital assistant server <b>106</b>. One or more processing modules <b>114</b> utilize data and models <b>116</b> to determine the user's intent based on natural language input and perform task execution based on inferred user intent. In some embodiments, DA-server <b>106</b> communicates with external services <b>120</b> through the network(s) <b>110</b> for task completion or information acquisition. The I/O interface to external services <b>118</b> facilitates such communications.

Examples of user device <b>104</b> include, but are not limited to, a handheld computer, a personal digital assistant (PDA), a tablet computer, a laptop computer, a desktop computer, a cellular telephone, a smart phone, an enhanced general packet radio service (EGPRS) mobile phone, a media player, a navigation device, a game console, a television, a remote control, or a combination of any two or more of these data processing devices or other data processing devices. More details on user device <b>104</b> are provided in reference to an exemplary user device <b>104</b> shown in <figref idref="DRAWINGS">FIG. <b>2</b></figref>.

User device <b>104</b> communicates with other devices <b>130</b> via communication network(s) <b>110</b>. Other devices <b>130</b> include computing devices (e.g., mobile phones, computers, or any other electronic devices with one or more processors, memory, and a communication interface) associated with users different from the user of user device <b>104</b>. Examples of communication network(s) <b>110</b> include local area networks (LAN) and wide area networks (WAN) such as the Internet. Communication network(s) <b>110</b> are, optionally, implemented using any known network protocol, including various wired or wireless protocols, such as Ethernet, Universal Serial Bus (USB), FIREWIRE, Global System for Mobile Communications (GSM), Enhanced Data GSM Environment (EDGE), code division multiple access (CDMA), time division multiple access (TDMA), Bluetooth, Wi-Fi, voice over Internet Protocol (VoIP), Wi-MAX, or any other suitable communication protocol.

Server system <b>108</b> is implemented on one or more standalone data processing apparatuses or a distributed network of computers. In some embodiments, server system <b>108</b> also employs various virtual devices and/or services of third party service providers (e.g., third-party cloud service providers) to provide the underlying computing resources and/or infrastructure resources of server system <b>108</b>.

Although the digital assistant shown in <figref idref="DRAWINGS">FIG. <b>1</b></figref> includes both a client-side portion (e.g., DA-client <b>102</b>) and a server-side portion (e.g., DA-server <b>106</b>), in some embodiments, the functions of a digital assistant are implemented as a standalone application installed on a user device. In addition, the division of functionalities between the client and server portions of the digital assistant can vary in different embodiments. For example, in some embodiments, DA-client <b>102</b> is a thin-client that provides only user-facing input and output processing functions, and delegates all other functionalities of the digital assistant to a backend server.

<figref idref="DRAWINGS">FIG. <b>2</b></figref> is a block diagram of a user device <b>104</b> in accordance with some embodiments. User device <b>104</b> includes a memory interface <b>202</b>, one or more processors <b>204</b>, and a peripherals interface <b>206</b>. The various components in user device <b>104</b> are coupled by one or more communication buses or signal lines. User device <b>104</b> includes various sensors, subsystems, and peripheral devices that are coupled to peripherals interface <b>206</b>. The sensors, subsystems, and peripheral devices gather information and/or facilitate various functionalities of user device <b>104</b>.

For example, a motion sensor <b>210</b>, a light sensor <b>212</b>, and a proximity sensor <b>214</b> are coupled to peripherals interface <b>206</b> to facilitate orientation, light, and proximity sensing functions. One or more other sensors <b>216</b>, such as a positioning system (e.g., a GPS receiver), a temperature sensor, a biometric sensor, a gyroscope, a compass, an accelerometer, and the like, are also connected to peripherals interface <b>206</b>, to facilitate related functionalities.

In some embodiments, a camera subsystem <b>220</b> and an optical sensor <b>222</b> are utilized to facilitate camera functions, such as taking photographs and recording video clips. Communication functions are facilitated through one or more wired and/or wireless communication subsystems <b>224</b>, which can include various communication ports, radio frequency receivers and transmitters, and/or optical (e.g., infrared) receivers and transmitters. An audio subsystem <b>226</b> is coupled to speakers <b>228</b> and a microphone <b>230</b> to facilitate voice-enabled functions, such as voice recognition, voice replication, digital recording, and telephony functions.

In some embodiments, an I/O subsystem <b>240</b> is also coupled to peripheral interface <b>206</b>. I/O subsystem <b>240</b> includes a touch screen controller <b>242</b> and/or other input controller(s) <b>244</b>. Touch-screen controller <b>242</b> is coupled to a touch screen <b>246</b>. Touch screen <b>246</b> and touch screen controller <b>242</b> can, for example, detect contact and movement or break thereof using any of a plurality of touch sensitivity technologies, such as capacitive, resistive, infrared, surface acoustic wave technologies, proximity sensor arrays, and the like. Other input controller(s) <b>244</b> can be coupled to other input/control devices <b>248</b>, such as one or more buttons, rocker switches, a thumb-wheel, an infrared port, a USB port, and/or a pointer device such as a stylus.

In some embodiments, memory interface <b>202</b> is coupled to memory <b>250</b>. Memory <b>250</b> can include high-speed random access memory and/or non-volatile memory, such as one or more magnetic disk storage devices, one or more optical storage devices, and/or flash memory (e.g., NAND or NOR).

In some embodiments, memory <b>250</b> stores an operating system <b>252</b>, a communication module <b>254</b>, a graphical user interface module <b>256</b>, a sensor processing module <b>258</b>, a phone module <b>260</b>, and applications <b>262</b>. Operating system <b>252</b> includes instructions for handling basic system services and for performing hardware dependent tasks. Communication module <b>254</b> facilitates communicating with one or more additional devices, one or more computers and/or one or more servers. Graphical user interface module <b>256</b> facilitates graphic user interface processing. Sensor processing module <b>258</b> facilitates sensor-related processing and functions. Phone module <b>260</b> facilitates phone-related processes and functions. Application module <b>262</b> facilitates various functionalities of user applications, such as electronic-messaging, web browsing, media processing, navigation, imaging, and/or other processes and functions.

As described in this specification, memory <b>250</b> also stores client-side digital assistant instructions (e.g., in a digital assistant client module <b>264</b>) and various user data <b>266</b> (e.g., user-specific vocabulary data, preference data, and/or other data such as the user's electronic address book, to-do lists, shopping lists, etc.) to provide the client-side functionalities of the digital assistant.

In various embodiments, digital assistant client module <b>264</b> is capable of accepting voice input (e.g., speech input), text input, touch input, and/or gestural input through various user interfaces (e.g., I/O subsystem <b>244</b>) of user device <b>104</b>. Digital assistant client module <b>264</b> is also capable of providing output in audio (e.g., speech output), visual, and/or tactile forms. For example, output can be provided as voice, sound, alerts, text messages, menus, graphics, videos, animations, vibrations, and/or combinations thereof. During operation, digital assistant client module <b>264</b> communicates with the digital assistant server using communication subsystems <b>224</b>.

In some embodiments, digital assistant client module <b>264</b> utilizes the various sensors, subsystems and peripheral devices to gather additional information from the surrounding environment of user device <b>104</b> to establish a context associated with a user, the current user interaction, and/or the current user input. In some embodiments, digital assistant client module <b>264</b> provides the context information or a subset thereof with the user input to the digital assistant server to help infer the user's intent. In some embodiments, the digital assistant also uses the context information to determine how to prepare and deliver outputs to the user.

In some embodiments, the context information that accompanies the user input includes sensor information, such as lighting, ambient noise, ambient temperature, images or videos of the surrounding environment, and the like. In some embodiments, the context information also includes the physical state of user device <b>104</b> (e.g., device orientation, device location, device temperature, power level, speed, acceleration, motion patterns, cellular signals strength, etc.). In some embodiments, information related to the software state of user device <b>104</b> (e.g., running processes, installed programs, past and present network activities, background services, error logs, resources usage, etc.) is provided to the digital assistant server as context information associated with a user input.

In some embodiments, digital assistant client module <b>264</b> selectively provides information (e.g., user data <b>266</b>) stored on user device <b>104</b> in response to requests from the digital assistant server. In some embodiments, digital assistant client module <b>264</b> also elicits additional input from the user via a natural language dialogue or other user interfaces upon request by digital assistant server <b>106</b>. Digital assistant client module <b>264</b> passes the additional input to digital assistant server <b>106</b> to help digital assistant server <b>106</b> in intent inference and/or fulfillment of the user's intent expressed in the user request.

In various embodiments, memory <b>250</b> includes additional instructions or fewer instructions. Furthermore, various functions of user device <b>104</b> may be implemented in hardware and/or in firmware, including in one or more signal processing and/or application specific integrated circuits.

<figref idref="DRAWINGS">FIG. <b>3</b>A</figref> is a block diagram of an example digital assistant system <b>300</b> in accordance with some embodiments. In some embodiments, digital assistant system <b>300</b> is implemented on a standalone computer system. In some embodiments, digital assistant system <b>300</b> is distributed across multiple computers. In some embodiments, some of the modules and functions of the digital assistant are divided into a server portion and a client portion, where the client portion resides on a user device (e.g., user device <b>104</b>) and communicates with the server portion (e.g., server system <b>108</b>) through one or more networks (e.g., network(s) <b>110</b>). In some embodiments, digital assistant system <b>300</b> is an embodiment of server system <b>108</b> (and/or digital assistant server <b>106</b>) shown in <figref idref="DRAWINGS">FIG. <b>1</b></figref>. It should be noted that digital assistant system <b>300</b> is only one example of a digital assistant system, and that digital assistant system <b>300</b> may have more or fewer components than shown, may combine two or more components, or may have a different configuration or arrangement of the components. The various components shown in <figref idref="DRAWINGS">FIG. <b>3</b>A</figref> may be implemented in hardware, software instructions for execution by one or more processors, firmware, including one or more signal processing and/or application specific integrated circuits, or a combination of thereof.

Digital assistant system <b>300</b> includes memory <b>302</b>, one or more processors <b>304</b>, an input/output (I/O) interface <b>306</b>, and a network communications interface <b>308</b>. These components communicate with one another over one or more communication buses or signal lines <b>310</b>.

In some embodiments, memory <b>302</b> includes a non-transitory computer readable storage medium, such as high-speed random access memory and/or a non-volatile storage medium (e.g., one or more magnetic disk storage devices, flash memory devices, or other non-volatile solid-state memory devices).

In some embodiments, I/O interface <b>306</b> couples input/output devices <b>316</b> of digital assistant system <b>300</b>, such as displays, keyboards, touch screens, and microphones, to user interface module <b>322</b>. I/O interface <b>306</b>, in conjunction with user interface module <b>322</b>, receives user inputs (e.g., voice input, keyboard inputs, touch inputs, etc.) and processes them accordingly. In some embodiments, digital assistant system <b>300</b> includes any of the components and I/O and communication interfaces described with respect to user device <b>104</b> in <figref idref="DRAWINGS">FIG. <b>2</b></figref> (e.g., when the digital assistant is implemented on a standalone user device). In some embodiments, digital assistant system <b>300</b> represents the server portion of a digital assistant implementation, and interacts with the user through a client-side portion residing on a user device (e.g., user device <b>104</b> shown in <figref idref="DRAWINGS">FIG. <b>2</b></figref>).

In some embodiments, network communications interface <b>308</b> includes wired communication port(s) <b>312</b> and/or wireless transmission and reception circuitry <b>314</b>. Wired communication port(s) receive and send communication signals via one or more wired interfaces such as Ethernet, Universal Serial Bus (USB), FIREWIRE, and the like. Wireless circuitry <b>314</b> receives and sends RF signals and/or optical signals from/to communications networks and other communications devices. The wireless communications, optionally, use any of a plurality of communications standards, protocols and technologies, such as GSM, EDGE, CDMA, TDMA, Bluetooth, Wi-Fi, VoIP, Wi-MAX, or any other suitable communication protocol. Network communications interface <b>308</b> enables communication between digital assistant system <b>300</b>, server system <b>108</b>, and other devices <b>130</b> via one or more networks (e.g., the Internet, an intranet, a wireless network, such as a cellular telephone network, a wireless local area network (LAN) or a metropolitan area network (MAN)).

In some embodiments, memory <b>302</b>, or the non-transitory computer readable storage media of memory <b>302</b>, stores programs, modules, instructions, and data structures including all or a subset of: an operating system <b>318</b>, a communications module <b>320</b>, a user interface module <b>322</b>, one or more applications <b>324</b>, and a digital assistant module <b>326</b>. One or more processors <b>304</b> execute these programs, modules, and instructions, and reads/writes from/to the data structures.

Operating system <b>318</b> (e.g., Darwin, RTXC, LINUX, UNIX, OS X, WINDOWS, or an embedded operating system such as VxWorks) includes various software components and/or drivers for controlling and managing general system tasks (e.g., memory management, storage device control, power management, etc.) and facilitates communications between various hardware, firmware, and software components.

Communications module <b>320</b> facilitates communications over network communications interface <b>308</b> between digital assistant system <b>300</b>, server system <b>108</b>, and other devices <b>130</b> (e.g., computing devices associated with users different from the user of user device <b>104</b>). For example, communication module <b>320</b>, optionally, communicates with communication interface <b>254</b> of user device <b>104</b> shown in <figref idref="DRAWINGS">FIG. <b>2</b></figref>. Communications module <b>320</b> also includes various components for handling data received by wireless circuitry <b>314</b> and/or wired communications port <b>312</b>.

User interface module <b>322</b> receives commands and/or inputs from a user via I/O interface <b>306</b> (e.g., from a keyboard, touch screen, pointing device, controller, and/or microphone), and generates user interface objects on a display. User interface module <b>322</b> also prepares and delivers outputs (e.g., speech, sound, animation, text, icons, vibrations, haptic feedback, light, etc.) to the user via I/O interface <b>306</b> (e.g., through displays, audio channels, speakers, touch-pads, etc.).

The one or more applications <b>324</b> include programs and/or modules that are configured to be executed by the one or more processors <b>304</b>. For example, if the digital assistant system is implemented on a standalone user device, one or more applications <b>324</b>, optionally, include user applications, such as games, a calendar application, a navigation application, or an email application. If digital assistant system <b>300</b> is implemented on a server farm, the one or more applications <b>324</b>, optionally, include resource management applications, diagnostic applications, or scheduling applications.

Memory <b>302</b> also stores digital assistant module <b>326</b> (or the server portion of a digital assistant). In some embodiments, digital assistant module <b>326</b> includes the following sub-modules, or a subset or superset thereof: an input/output processing module <b>328</b>, a speech-to-text (STT) processing module <b>330</b>, a natural language processing module <b>332</b>, a dialogue flow processing module <b>340</b>, a task flow processing module <b>342</b>, a service processing module <b>346</b>, and an auto response module <b>350</b>. Each of these modules has access to one or more of the following data and models of the digital assistant <b>326</b>, or a subset or superset thereof: ontology <b>334</b>, vocabulary index <b>336</b>, user data <b>338</b>, task flow models <b>344</b>, service models <b>348</b>, and user log <b>360</b>.

In some embodiments, using the processing modules, data, and models implemented in digital assistant module <b>326</b>, digital assistant system <b>300</b> performs at least some of the following: identifying a user's intent expressed in a natural language input received from the user; actively eliciting and obtaining information needed to fully infer the user's intent (e.g., by disambiguating words, names, intentions, etc.); determining the task flow for fulfilling the inferred intent; and executing the task flow to fulfill the inferred intent. In some embodiments, the digital assistant also takes appropriate actions when a satisfactory response was not or could not be provided to the user for various reasons.

In some embodiments, as shown in <figref idref="DRAWINGS">FIG. <b>3</b>B</figref>, I/O processing module <b>328</b> interacts with the user through I/O devices <b>316</b> in <figref idref="DRAWINGS">FIG. <b>3</b>A</figref> or with a user device (e.g., user device <b>104</b> in <figref idref="DRAWINGS">FIG. <b>1</b></figref>) through network communications interface <b>308</b> in <figref idref="DRAWINGS">FIG. <b>3</b>A</figref> to obtain user input (e.g., a speech input) and to provide responses (e.g., as speech outputs) to the user input. I/O processing module <b>328</b>, optionally, obtains context information associated with the user input from the user device, along with or shortly after the receipt of the user input. The context information includes user-specific data, vocabulary, and/or preferences relevant to the user input. In some embodiments, the context information also includes software and hardware states of the device (e.g., user device <b>104</b> in <figref idref="DRAWINGS">FIG. <b>1</b></figref>) at the time the user request is received, and/or information related to the surrounding environment of the user at the time that the user request was received. In some embodiments, I/O processing module <b>328</b> also sends follow-up questions to, and receives answers from, the user regarding the user request. When a user request is received by I/O processing module <b>328</b> and the user request contains a speech input, I/O processing module <b>328</b> forwards the speech input to STT processing module <b>330</b> for speech-to-text conversion.

STT processing module <b>330</b> receives speech input (e.g., a user utterance captured in a voice recording) through I/O processing module <b>328</b>. In some embodiments, STT processing module <b>330</b> uses various acoustic and language models to recognize the speech input as a sequence of phonemes, and ultimately, a sequence of words or tokens written in one or more languages. The speech-to-text processing module <b>330</b> can be implemented using any suitable speech recognition techniques, acoustic models, and language models such as Hidden Markov Models, Dynamic Time Warping (DTW) based speech recognition, and other statistical and/or analytical techniques. In some embodiments, speech-to-text processing can be performed at least partially by a third party service or on the user's device. Once STT processing module <b>330</b> obtains the result of the speech-to-text processing (e.g., a sequence of words or tokens), STT processing module <b>330</b> passes the result to natural language processing module <b>332</b> for intent inference.

More details on the speech-to-text processing are described in U.S. Utility application Ser. No. 13/236,942 for “Consolidating Speech Recognition Results,” filed on Sep. 20, 2011, the entire disclosure of which is incorporated herein by reference.

Natural language processing module <b>332</b> (sometimes herein also called a “natural language processor”) of the digital assistant takes the sequence of words or tokens (or token sequence) generated by STT processing module <b>330</b>, and attempts to associate the token sequence with one or more actionable intents recognized by the digital assistant. An “actionable intent” represents a task that can be performed by the digital assistant and has an associated task flow implemented in task flow models <b>344</b>. The associated task flow is a series of programmed actions and steps that the digital assistant takes in order to perform the task. The scope of a digital assistant's capabilities is dependent on the number and variety of task flows that have been implemented and stored in task flow models <b>344</b> or, in other words, on the number and variety of actionable intents that the digital assistant recognizes. The effectiveness of the digital assistant, however, is also dependent on the digital assistant's ability to infer the correct actionable intent(s) from the user request expressed in natural language.

In some embodiments, in addition to the token sequence obtained from STT processing module <b>330</b>, natural language processor <b>332</b> also receives context information associated with the user request (e.g., from I/O processing module <b>328</b>). Natural language processor <b>332</b>, optionally, uses the context information to clarify, supplement, and/or further define the information contained in the token sequence received from STT processing module <b>330</b>. The context information includes, for example, user preferences, hardware and/or software states of the user device, sensor information collected before, during, or shortly after the user request, prior interactions (e.g., dialogue) between the digital assistant and the user, and the like.

In some embodiments, the natural language processing is based on ontology <b>334</b>. Ontology <b>334</b> is a hierarchical structure containing many nodes, each node representing either an “actionable intent” or a “property” relevant to one or more of the “actionable intents” or other “properties.” As noted above, an “actionable intent” represents a task that the digital assistant is capable of performing (i.e., it is actionable or can be acted on). A “property” represents a parameter associated with an actionable intent or a sub-aspect of another property. A linkage between an actionable intent node and a property node in ontology <b>334</b> defines how a parameter represented by the property node pertains to the task represented by the actionable intent node.

In some embodiments, ontology <b>334</b> is made up of actionable intent nodes and property nodes. Within ontology <b>334</b>, each actionable intent node is linked to one or more property nodes either directly or through one or more intermediate property nodes. Similarly, each property node is linked to one or more actionable intent nodes either directly or through one or more intermediate property nodes. For example, as shown in <figref idref="DRAWINGS">FIG. <b>3</b>C</figref>, ontology <b>334</b> optionally includes a “restaurant reservation” node—an actionable intent node. Property nodes “restaurant,” “date/time” (for the reservation), and “party size” are each directly linked to the actionable intent node (e.g., the “restaurant reservation” node). In addition, property nodes “cuisine,” “price range,” “phone number,” and “location” are sub-nodes of the property node “restaurant,” and are each linked to the “restaurant reservation” node through the intermediate property node “restaurant.” For another example, as shown in <figref idref="DRAWINGS">FIG. <b>3</b>C</figref>, ontology <b>334</b> may also include a “set reminder” node (e.g., another actionable intent node). Property nodes “date/time” (for the setting the reminder) and “subject” (for the reminder) are each linked to the “set reminder” node. Since the property “date/time” is relevant to both the task of making a restaurant reservation and the task of setting a reminder, the property node “date/time” is linked to both the “restaurant reservation” node and the “set reminder” node in ontology <b>334</b>.

An actionable intent node, along with its linked property nodes, is sometimes described as a “domain.” In the present discussion, each domain is associated with a respective actionable intent, and refers to the group of nodes (and the relationships therebetween) associated with the particular actionable intent. For example, ontology <b>334</b> shown in <figref idref="DRAWINGS">FIG. <b>3</b>C</figref> includes an example of a restaurant reservation domain <b>362</b> and an example of a reminder domain <b>364</b> within ontology <b>334</b>. The restaurant reservation domain includes the actionable intent node “restaurant reservation,” property nodes “restaurant,” “date/time,” and “party size,” and sub-property nodes “cuisine,” “price range,” “phone number,” and “location.” Reminder domain <b>364</b> includes the actionable intent node “set reminder,” and property nodes “subject” and “date/time.” In some embodiments, ontology <b>334</b> is made up of many domains. Each domain optionally shares one or more property nodes with one or more other domains. For example, the “date/time” property node is, optionally, associated with many different domains (e.g., a scheduling domain, a travel reservation domain, a movie ticket domain, etc.), in addition to restaurant reservation domain <b>362</b> and reminder domain <b>364</b>.

While <figref idref="DRAWINGS">FIG. <b>3</b>C</figref> illustrates two example domains within ontology <b>334</b>, other domains (or actionable intents) include, for example, “initiate a phone call,” “find directions,” “schedule a meeting,” “send a message,” and “provide an answer to a question,” and so on. A “send a message” domain is associated with a “send a message” actionable intent node, and optionally further includes property nodes such as “recipient(s),” “message type,” and “message body.” The property node “recipient” is optionally further defined, for example, by the sub-property nodes such as “recipient name” and “message address.”

In some embodiments, the ontology <b>334</b> includes all the domains (and hence actionable intents) that the digital assistant is capable of understanding and acting upon. In some embodiments, ontology <b>334</b> is optionally modified, such as by adding or removing entire domains or nodes, or by modifying relationships between the nodes within ontology <b>334</b>.

In some embodiments, nodes associated with multiple related actionable intents are optionally clustered under a “super domain” in ontology <b>334</b>. For example, a “travels” super domain optionally includes a cluster of property nodes and actionable intent nodes related to travel. The actionable intent nodes related to travel optionally include “airline reservation,” “hotel reservation,” “car rental,” “get directions,” “find points of interest,” and so on. The actionable intent nodes under the same super domain (e.g., the “travels” super domain) sometimes have many property nodes in common. For example, the actionable intent nodes for “airline reservation,” “hotel reservation,” “car rental,” “get directions,” “find points of interest” sometimes share one or more of the property nodes “start location,” “destination,” “departure date/time,” “arrival date/time,” and “party size.”

In some embodiments, each node in ontology <b>334</b> is associated with a set of words and/or phrases that are relevant to the property or actionable intent represented by the node. The respective set of words and/or phrases associated with each node is the so-called “vocabulary” associated with the node. The respective set of words and/or phrases associated with each node can be stored in vocabulary index <b>336</b> in association with the property or actionable intent represented by the node. For example, returning to <figref idref="DRAWINGS">FIG. <b>3</b>B</figref>, the vocabulary associated with the node for the property of “restaurant” optionally includes words such as “food,” “drinks,” “cuisine,” “hungry,” “eat,” “pizza,” “fast food,” “meal,” and so on. For another example, the vocabulary associated with the node for the actionable intent of “initiate a phone call” optionally includes words and phrases such as “call,” “phone,” “dial,” “call this number,” “make a call to,” and so on. The vocabulary index <b>336</b>, optionally, includes words and phrases in different languages.

Natural language processor <b>332</b> receives the token sequence (e.g., a text string) from STT processing module <b>330</b> and determines what nodes are implicated by the words in the token sequence. In some embodiments, if a word or phrase in the token sequence is found to be associated with one or more nodes in ontology <b>334</b> (via vocabulary index <b>336</b>), the word or phrase will “trigger” or “activate” those nodes. Based on the quantity and/or relative importance of the activated nodes, natural language processor <b>332</b> will select one of the actionable intents as the task that the user intended the digital assistant to perform. In some embodiments, the domain that has the most “triggered” nodes is selected. In some embodiments, the domain having the highest confidence value (e.g., based on the relative importance of its various triggered nodes) is selected. In some embodiments, the domain is selected based on a combination of the number and the importance of the triggered nodes. In some embodiments, additional factors are considered in selecting the node as well, such as whether the digital assistant has previously correctly interpreted a similar request from a user.

In some embodiments, the digital assistant also stores names of specific entities in vocabulary index <b>336</b>, so that when one of these names is detected in the user request, natural language processor <b>332</b> will be able to recognize that the name refers to a specific instance of a property or sub-property in the ontology. In some embodiments, the names of specific entities are names of businesses, restaurants, people, movies, and the like. In some embodiments, the digital assistant searches and identifies specific entity names from other data sources, such as the user's address book, a movies database, a musicians database, and/or a restaurant database. In some embodiments, when natural language processor <b>332</b> identifies that a word in the token sequence is a name of a specific entity (e.g., a name in the user's address book), that word is given additional significance in selecting the actionable intent within the ontology for the user request.

For example, when the words “Mr. Santo” are recognized in a user request and the last name “Santo” is found in vocabulary index <b>336</b> as one of the contacts in the user's address book, then it is likely that the user request corresponds to a “send a message” or an “initiate a phone call” domain. For another example, when the words “ABC Café” are found in a user request and the term “ABC Café” is found in vocabulary index <b>336</b> as the name of a particular restaurant in the user's city, then it is likely that the user request corresponds to a “restaurant reservation” or a “find restaurants” domain.

User data <b>338</b> includes user-specific information, such as user-specific vocabulary, user preferences, user address or home location, user's default and secondary languages, user's address book, and other short-term or long-term information for each user. In some embodiments, natural language processor <b>332</b> uses the user-specific information to supplement the information contained in a user input to further define the user intent. For example, for a user request “invite my friends to my birthday party,” natural language processor <b>332</b> is able to access user data <b>338</b> to determine who the “friends” are and when and where the “birthday party” would be held, rather than requiring the user to provide such information explicitly in his/her request.

Other details of searching an ontology based on a token string is described in U.S. Utility application Ser. No. 12/341,743 for “Method and Apparatus for Searching Using An Active Ontology,” filed Dec. 22, 2008, the entire disclosure of which is incorporated herein by reference.

In some embodiments, once natural language processor <b>332</b> identifies an actionable intent (or domain) based on the user request, natural language processor <b>332</b> generates a structured query to represent the identified actionable intent. In some embodiments, the structured query includes parameters for one or more nodes within the domain for the actionable intent, and at least some of the parameters are populated with the specific information and requirements specified in the user request. For example, the user states to the DA, “Make me a dinner reservation at a sushi place at 7.” In this case, natural language processor <b>332</b> may be able to correctly identify the actionable intent to be “restaurant reservation” based on the user input. According to the ontology, a structured query for a “restaurant reservation” domain optionally includes parameters such as {Cuisine}, {Time}, {Date}, {Party Size}, and the like. In some embodiments, based on the information contained in the user's utterance, natural language processor <b>332</b> generates a partial structured query for the restaurant reservation domain, where the partial structured query includes the parameters {Cuisine=Sushi} and {Time=7 PM}. In this example, the user's utterance, however, contains insufficient information to complete the structured query associated with the domain. Therefore, other necessary parameters such as {Party Size} and {Date} are not specified in the structured query based on the information currently available. In some embodiments, natural language processor <b>332</b> populates some parameters of the structured query with received context information. For example, in some embodiments, if the user requested a sushi restaurant “near me,” natural language processor <b>332</b> populates a {location} parameter in the structured query with GPS coordinates from user device <b>104</b>.

In some embodiments, natural language processor <b>332</b> passes the structured query (including any completed parameters) to task flow processing module <b>342</b> (sometimes herein also called a “task flow processor”). Task flow processor <b>342</b> is configured to receive the structured query from natural language processor <b>332</b>, complete the structured query, if necessary, and perform the actions required to “complete” the user's ultimate request. In some embodiments, the various procedures necessary to complete these tasks are provided in task flow models <b>344</b>. In some embodiments, task flow models <b>344</b> include procedures for obtaining additional information from the user, and task flows for performing actions associated with the actionable intent.

As described above, in order to complete a structured query, task flow processor <b>342</b> sometimes needs to initiate additional dialogue with the user in order to obtain additional information, and/or disambiguate potentially ambiguous utterances. When such interactions are necessary, task flow processor <b>342</b> invokes dialogue flow processing module <b>340</b> (sometimes herein also called a “dialogue processor”) to engage in a dialogue with the user. In some embodiments, dialogue processor <b>340</b> determines how (and/or when) to ask the user for the additional information, and receives and processes the user responses. The questions are provided to and answers are received from the users through I/O processing module <b>328</b>. In some embodiments, dialogue processor <b>340</b> presents dialogue output to the user via audio and/or visual output, and receives input from the user via spoken or physical (e.g., clicking) responses. Continuing with the example above, when task flow processor <b>342</b> invokes dialogue processor <b>340</b> to determine the “party size” and “date” information for the structured query associated with the domain “restaurant reservation,” dialogue processor <b>340</b> generates questions, such as “For how many people?” and “On which day?,” to pass to the user. Once answers are received from the user, the dialogue processor <b>340</b> can then populate the structured query with the missing information, or pass the information to task flow processor <b>342</b> to complete the missing information from the structured query.

Once task flow processor <b>342</b> has completed the structured query for an actionable intent, task flow processor <b>342</b> proceeds to perform the ultimate task associated with the actionable intent. Accordingly, task flow processor <b>342</b> executes the steps and instructions in the task flow model according to the specific parameters contained in the structured query. For example, the task flow model for the actionable intent of “restaurant reservation,” optionally, includes steps and instructions for contacting a restaurant and actually requesting a reservation for a particular party size at a particular time. For example, using a structured query, such as {restaurant reservation, restaurant=ABC Café, date=Mar. 12, 2012, time=7 PM, party size=5}, task flow processor <b>342</b>, optionally, performs the steps of: (1) logging onto a server of the ABC Café or a restaurant reservation system such as OPENTABLE®; (2) entering the date, time, and party size information in a form on the website; (3) submitting the form; and (4) making a calendar entry for the reservation in the user's calendar.

In some embodiments, task flow processor <b>342</b> employs the assistance of a service processing module <b>346</b> (sometimes herein also called a “service processor”) to complete a task requested in the user input or to provide an informational answer requested in the user input. For example, service processor <b>346</b> can act on behalf of task flow processor <b>342</b> to make a phone call, set a calendar entry, invoke a map search, invoke or interact with other user applications installed on the user device, and invoke or interact with third party services (e.g., a restaurant reservation portal, a social networking website, a banking portal, etc.). In some embodiments, the protocols and application programming interfaces (API) required by each service can be specified by a respective service model among services models <b>348</b>. Service processor <b>346</b> accesses the appropriate service model for a service and generates requests for the service in accordance with the protocols and APIs required by the service according to the service model.

For example, if a restaurant has enabled an online reservation service, the restaurant can submit a service model specifying the necessary parameters for making a reservation and the APIs for communicating the values of the necessary parameter to the online reservation service. When requested by task flow processor <b>342</b>, service processor <b>346</b> can establish a network connection with the online reservation service using the web address stored in the service model, and send the necessary parameters of the reservation (e.g., time, date, party size) to the online reservation interface in a format according to the API of the online reservation service.

In some embodiments, natural language processor <b>332</b>, dialogue processor <b>340</b>, and task flow processor <b>342</b> are used collectively and iteratively to infer and define the user's intent, obtain information to further clarify and refine the user intent, and finally generate a response (e.g., an output to the user, or the completion of a task) to fulfill the user's intent.

In some embodiments, after all of the tasks needed to fulfill the user's request have been performed, digital assistant <b>326</b> formulates a confirmation response, and sends the response to the user through I/O processing module <b>328</b>. If the user request seeks an informational answer, the confirmation response presents the requested information to the user. In some embodiments, the digital assistant also requests the user to indicate whether the user is satisfied with the response produced by digital assistant <b>326</b>.

Natural language processor <b>332</b> receives a token sequence from STT processing module <b>330</b> corresponding to a speech input from a user of user device <b>104</b> (<figref idref="DRAWINGS">FIG. <b>1</b></figref>). In some embodiments, natural language processor <b>332</b> infers that the speech input includes instructions for automatically responding to a subsequent incoming communication from one or more specified senders. When the instructions at least include (1) one or more specified senders and (2) a specified action, the instructions trigger a task flow associated with auto response domain <b>400</b> of ontology <b>334</b>, discussed in more detail below in relation to <figref idref="DRAWINGS">FIG. <b>4</b></figref>. In some other embodiments, natural language processor <b>332</b> infers that a respective domain distinct from auto response domain <b>400</b> is triggered, and digital assistant <b>326</b> proceeds with the task flow model associated with the respective domain (e.g., the restaurant reservation domain discussed above).

In some embodiments, digital assistant <b>326</b> includes an auto response module <b>350</b>. In some embodiments, auto response module <b>350</b> is a component of task flow processor <b>342</b>. In some other embodiments, auto response module <b>350</b> is separate from task flow processor <b>342</b>. Auto response module <b>350</b> is configured to perform steps to fulfill a user request that triggers auto response domain <b>400</b>. In other words, auto response module <b>350</b> is configured to perform a task flow related to auto response domain <b>400</b>.

After natural language processor <b>332</b> determines that auto response domain <b>400</b> is triggered, auto response module <b>350</b> obtains the instructions from natural language processor <b>332</b> and performs a specified action, or causes a specified action to be performed, in response to reception of a subsequent incoming communication from one of the one or more specified senders. In some embodiments, auto response module <b>350</b> includes an instructions module <b>352</b>, a determination module <b>354</b>, a composition module <b>356</b>, and a performance module <b>358</b>.

Instructions module <b>352</b> is configured to store the instructions included in the speech input for responding to an incoming communication. The stored instructions at least include the specified action and the one or more specified senders. In some embodiments, the stored instructions, optionally, include one or more specified communication types, an expiration period for the instructions, and/or a condition precedent to performance of the instructions. In some embodiments, instructions module <b>352</b> includes a memory for storing the instructions received from the user. In some other embodiments, instructions module <b>352</b> stores the instructions in a memory separate from instructions module <b>352</b>. In some embodiments, when included in the speech input (i.e., the instructions), instructions module <b>352</b> is also configured to store an expiration period (or duration) for the instructions (e.g., within the next two days or by 5:00 PM today) and a condition precedent to performance of the specified action. Instructions module <b>352</b> is also configured to automatically delete the instructions upon performance of the specified action or elapse of the expiration period. In some embodiments, the instructions are deleted immediately upon performance or elapse of the expiration period without human intervention or instruction.

In some embodiments, user device <b>104</b> receives an incoming communication via communication network(s) <b>110</b> from one of other devices <b>130</b> that associated with a user different from the user of user device <b>104</b>. In some embodiments, determination module <b>354</b> is configured to ascertain whether the sender of a subsequent incoming communication (e.g., the sender of a phone call, SMS, or email) is one of the one or more specified senders indicated in the instructions. In one embodiment, determination module <b>354</b> ascertains whether the sender of a subsequent incoming communication is one of the one or more specified senders based at least in part on the user's address book. For example, determination module <b>354</b> compares the phone number corresponding to the incoming communication with the phone number in the user's address corresponding to the specified user. In another embodiment, determination module <b>354</b> ascertains whether the sender of a subsequent incoming communication is one of the one or more specified senders based at least in part on caller identification information associated with the sender of the subsequent incoming communication. In another embodiment, determination module <b>354</b> identifies an email address (or other unique identifier) associated with the subsequent incoming communication (e.g., a VoIP call or other Internet based communication) and ascertains whether the sender of a subsequent incoming communication is one of the one or more specified senders based at least in part on the identified email address.

In a further embodiment, determination module <b>354</b> ascertains whether the sender of a subsequent incoming communication is one of the one or more specified senders based at least in part on post-processing of the subsequent incoming communication. For example, determination module <b>354</b> determines or infers the identity of the sender of the subsequent incoming communication based on a name, telephone number, email address, or other identifying information left in a voicemail or voice message such as, “Hi this is John White, please call me back.” In another example, determination module <b>354</b> determines the identity of the sender of the subsequent incoming communication based on a name in a signature block of an email. In another example, determination module <b>354</b> determines the identity of the sender of the subsequent incoming communication based on a name, telephone number, email address, or other identifying information left in an SMS such as “Hi this is Jack White, text me back with the address for the gig tonight.”

In some embodiments, determination module <b>354</b> is also configured to determine whether the subsequent incoming communication is of a communication type specified by the instructions. For example, the user states to the DA, “If Mom texts, text her back that I'm on my way home.” In this example, the specified action (e.g., sending Mom a text) is only to be performed when a text message or SMS is received from Mom. In another example, the user states to the DA, “If my wife calls, let her know that I'm at the gym and will be home soon.” In this example, the specified action (e.g., letting the user's wife know that the user is at the gym and will be home soon) is only to be performed when a phone call is received from the user's wife.

In some embodiments, when the instructions indicate an expiration period, determination module <b>354</b> is further configured to determine whether the subsequent incoming communication is received within the expiration period. In some embodiments, when the instructions indicate a condition precedent to performance of the specified action, determination module <b>354</b> is further configured to determine whether the condition precedent is satisfied prior to or concurrent with receiving the subsequent incoming communication.

Composition module <b>356</b> is configured to compose a response to the subsequent incoming communication based on the instructions included in the speech input. In some embodiments, composition module <b>356</b> utilizes contextual information (e.g., location, past patterns or behavior, or a calendar associated with the user) when composing the response. For example, suppose the user of user device <b>104</b> asks the DA, “If my wife contacts me, text her that ‘I'm on my way home.’” In this example, after determining that a subsequent incoming communication is received from the user's wife (e.g., based on one of the procedures described above), the digital assistant composes a text message to the user's wife based at least in part on the instructions and location information associated with the user. For example, the text message composed by composition module <b>356</b> states, “Hi Honey. I'm on my way home and should be there in approximately fifteen minutes based on traffic.” In this example, the fifteen minute period is estimated by the digital assistant based on the current location of the user, the location of the user's home, and/or current traffic conditions.

In some embodiments, performance module <b>358</b> is configured to perform the action specified by the instructions after determination module <b>354</b> determines that the sender of the subsequent incoming communication is one of the one or more specified senders. In some other embodiments, performance module <b>358</b> is configured to cause the action specified by the instructions to be performed after determination module <b>354</b> determines that the subsequent incoming communication is one of the one or more specified communication types. For example, the specified action is sending a voice message to the sender, sending an SMS or text message to the sender, sending an MMS to the sender, sending an instant message to the sender, sending an email to the sender, sending some other form of electronic or non-electronic communication to the sender, sending an event or calendar invite to the sender, sending or sharing media content (e.g., an audio file, a video clip, a photograph, a URL, or the like), sharing one or more calendar or appointment entries with the sender, or sharing one or more other custom attributes (e.g., other items of information or media content defined by the user) with the sender. In some embodiments, performance module is configured to respond by default to a subsequent incoming communication using the same means of communication as the subsequent incoming communication.

More details on the digital assistant can be found in the U.S. Utility application Ser. No. 12/987,982, entitled “Intelligent Automated Assistant,” filed Jan. 18, 2010, and also in U.S. Utility Application No. 61/493,201, entitled “Generating and Processing Data Items That Represent Tasks to Perform,” filed Jun. 3, 2011, the entire disclosures of which are incorporated herein by reference.

<figref idref="DRAWINGS">FIG. <b>4</b></figref> illustrates an auto response domain <b>400</b> within ontology <b>334</b> associated with an actionable intent <b>402</b> of automatically performing a specified action in response to reception of a subsequent incoming communication from one of the one or more specified senders (sometimes herein also called the “auto response” actionable intent).

Specified sender property node <b>404</b> indicates a sender of a subsequent incoming communication. In some embodiments, the specified sender node <b>404</b> includes sub-property nodes identifying the specified sender such as a name in the user's address book, a phone number, an email address, and the like. Specified action node <b>406</b> indicates the action to be performed when an incoming communication from the specified sender is received. In some embodiments, the specified action node <b>406</b> includes sub-nodes identifying details <b>414</b> (or information) to be included in the automatic response and the action type <b>416</b> to be performed.

In some embodiments, details sub-node <b>414</b> includes text or recorded spoken words from the speech input, a digitized or text-to-speech version of a text input from the user, and/or the current location of user device <b>104</b> (<figref idref="DRAWINGS">FIG. <b>1</b></figref>) for inclusion in the automatic response. In some embodiments, if the user's request includes insufficient details or instructions for composing the automatic response message, auto response module <b>350</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) is configured to cause dialogue processing module <b>340</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) to initiate a dialogue with the user to elicit additional details or instructions for composing a complete automatic response message. In some other embodiments, if the user's request includes insufficient details or instructions for composing the auto response message, auto response module <b>350</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) is configured to cause composition module <b>356</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) to complete any non-essential details not included in the instructions in order to compose the automatic response message. For example, composition module <b>356</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) employs the use of context information associated with the user such as the user's address book, location information, pattern or behavior information, user log, or calendar entries to compose the complete automatic response message.

In some embodiments, action type sub-node <b>416</b> specifies the type of action to be performed such as sending/sharing a voicemail or voice message, SMS or text message, MMS, email, event invite, media content, one or more calendar entries, or one or more custom attributes to/with the specified sender. In some embodiments, if the user's request states that the DA is to communicate information to a specified sender but does not specify a means of communication, either a most frequent or default means of communication is used for the response message.

For example, the user of user device <b>104</b> states to the DA, “If my parents try to contact me, text them the address of my new apartment and, also, let them know that I'll call them back.” In this case, natural language processor <b>332</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) identifies actionable intent as the “auto response” actionable intent <b>402</b> because the speech input includes one or more specified senders (e.g., either of the user's parents) and a specified action to be performed (e.g., sending a text message). According to ontology <b>334</b>, a structured query for auto response domain <b>400</b> includes parameters such as {specified sender <b>404</b>}, {details <b>414</b>}, and {action type <b>416</b>}. For example, using a structured query, such as {auto response, specified sender=parents, details=address of user's apartment and “will call back,” action type=SMS or text message}, task flow processor <b>342</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>), or a component thereof, performs the steps of: (1) storing the instructions included in the speech input; (2) receiving a subsequent incoming communication (e.g., a text message or phone call); (3) determining whether the sender of a subsequent incoming communication is the specified sender (e.g., either of the user's parents); (4) composing a responsive text message in accordance with the details (or information) provided in the instructions (e.g., “My address is 123 Elwynn Forest Drive, Sunnyvale, CA 94086. I'll call y'all back when I'm free.”); (5) causing the text message to be sent to one or both of the user's parent; and (6) automatically deleting the instructions after causing the text message to be sent.

Expiration period node <b>408</b> specifies a time period in which a subsequent incoming communication from the one or more specified senders must be received. For example, the user of user device <b>104</b> states to the DA, “If Gary attempts to contact me in the next 30 minutes, email him with the next time slot I'm available today for a meeting.” In this case, natural language processor <b>332</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) identifies actionable intent as the “auto response” actionable intent <b>402</b> because the speech input includes one or more specified senders (e.g., Gary) and a specified action to be performed (e.g., sending a proposed meeting time). According to ontology <b>334</b>, a structured query for auto response domain <b>400</b> includes parameters such as {specified sender <b>404</b>}, {details <b>414</b>}, {action type <b>416</b>}, and {expiration period <b>408</b>}. For example, using a structured query, such as {auto response, specified sender=Gary, details=next available meeting time, action type=email, expiration period=30 minutes}, task flow processor <b>342</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>), or a component thereof, performs the steps of: (1) storing the instructions included in the speech input; (2) receiving a subsequent incoming communication (e.g., a text message, phone call, or email); (3) determining whether the sender of a subsequent incoming communication is the specified sender (e.g., Gary); (4) determining whether the subsequent incoming communication was received within the expiration period (e.g., within 30 minutes of receiving the instructions); (5) composing a responsive email in accordance with the details (or information) provided in the instructions and the user's calendar (e.g., “Hi Gary. My schedule indicates that I'm next available to meet at 1 PM EDT this afternoon.”); (6) causing the email to be sent to Gary; and (7) automatically deleting the instructions after causing the email to be sent.

Condition node <b>410</b> specifies a condition that must be satisfied prior to performing the specified action. For example, the user of user device <b>104</b> states to the DA, “If Suzie tries to get in touch with me, send her directions to Half Moon Bay from her home address, but only if it's over 75° in Half Moon Bay when she contacts me.” In this case, natural language processor <b>332</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) identifies the actionable intent as “auto response” actionable intent <b>402</b> because the speech input includes one or more specified senders (e.g., Suzie) and a specified action to be performed (e.g., sending directions). According to ontology <b>334</b>, a structured query for auto response domain <b>400</b> includes parameters such as {specified sender <b>404</b>}, {specified action <b>406</b>}, {details <b>414</b>}, and {condition precedent <b>410</b>}. For example, using a structured query, such as {auto response, specified sender=Suzie, specified action=send directions, details=directions to Half Moon Bay from Suzie's home address, condition precedent=temperature in Half Moon Bay over 75° when Suzie contacts}, task flow processor <b>342</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>), or a component thereof, performs the steps of: (1) storing the instructions included in the speech input; (2) receiving a subsequent incoming communication (e.g., a text message, phone call or email); (3) determining whether the sender of a subsequent incoming communication is the specified sender (e.g., Suzie); (4) determining whether the condition precedent is satisfied upon reception of the subsequent incoming communication (e.g., the temperature in Half Moon Bay is over 75°); (5) causing directions from Suzie's home address to Half Moon Bay to be sent to Suzie (e.g., using a default or most frequent means of communication); and (6) automatically deleting the instructions after causing the directions to be sent.

Specified incoming communication type node <b>412</b> indicates a means of communication by which the subsequent incoming communication must be received in order to perform the specified action. In some embodiments, specified incoming communication type node <b>412</b> includes sub-nodes identifying the communication means such as SMS or text message, phone call, email, VoIP, video call, and the like. For example, the user of user device <b>104</b> states to the DA, “If Varun texts me, let him know I'll be online in 15 minutes.” In this case, natural language processor <b>332</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) identifies the actionable intent as “auto response” actionable intent <b>402</b> because the speech input includes one or more specified senders (e.g., Varun) and a specified action to be performed (e.g., sending an informative message). According to ontology <b>334</b>, a structured query for auto response domain <b>400</b> includes parameters such as {specified sender <b>404</b>}, {specified action <b>406</b>}, {details <b>414</b>}, and {specified incoming communication type <b>412</b>}. For example, using a structured query, such as {auto response, specified sender=Varun, specified action=sending an informative message, details=the user will be online in 15 minutes, specified incoming communication type=SMS or text message}, task flow processor <b>342</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>), or a component thereof, performs the steps of: (1) storing the instructions included in the speech input; (2) receiving a subsequent incoming communication (e.g., a text message, phone call or email); (3) determining whether the sender of a subsequent incoming communication is the specified sender (e.g., Varun); (4) determining whether the subsequent incoming communication is the specified incoming communication type (e.g., an SMS or text message); (5) composing a responsive message in accordance with the details (or information) provided in the instructions (e.g., “Hey Varun. I'll be online in 15 minutes.”); (6) causing the informative message to be sent to David (e.g., using a default or most frequent means of communication); and (7) automatically deleting the instructions after causing the informative message to be sent.

<figref idref="DRAWINGS">FIG. <b>5</b></figref> illustrates a flow diagram of a method <b>500</b> of operating a digital assistant in accordance with some embodiments. In some embodiments, method <b>500</b> is performed at an electronic device including one or more processors and memory (e.g., a respective DA-client <b>102</b> or DA-server <b>106</b>, <figref idref="DRAWINGS">FIG. <b>1</b></figref>). In some embodiments, method <b>500</b> is performed at digital assistant <b>326</b> illustrated in <figref idref="DRAWINGS">FIGS. <b>3</b>A-<b>3</b>B</figref>. In some embodiments, method <b>500</b> is governed by a set of instructions stored in memory (e.g., a non-transitory computer readable storage medium) that are executed by the one or more processors of the electronic device.

The electronic device (e.g., user device <b>104</b>) receives a speech input from a user of user device <b>104</b> (e.g., the speech input is received at I/O processing module <b>328</b>, <figref idref="DRAWINGS">FIG. <b>3</b>A</figref>). For example, the user states to the digital assistant (DA), “If Christina texts, let her know that I'm currently driving and will be there soon.” In turn, I/O processing module <b>328</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) sends the speech input to STT processing module <b>330</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>). After processing the speech input, STT processing module <b>330</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) sends a token sequence representative of the speech input to natural language processor <b>332</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>).

Natural language processor <b>332</b> receives (<b>502</b>) the token sequence from STT processing module <b>330</b> and attempts to associate the token sequence with one or more actionable intents recognized by the digital assistant.

Natural language processor <b>332</b> determines (<b>504</b>) whether the speech input includes instructions for automatically responding to a subsequent incoming communication from one or more specified senders. When the instructions at least include (1) one or more specified senders (e.g., Christina) and (2) a specified action (e.g., an informative response), the instructions trigger a task flow associated with auto response domain <b>400</b> of ontology <b>334</b>.

Upon determining that the speech input does not include instructions for automatically responding to a subsequent incoming communication from one or more specified senders (“No” branch), the digital assistant performs (<b>506</b>) one or more other processes associated with task flows different from the task flow associated with auto response domain <b>400</b> (e.g., the restaurant reservation domain discussed above).

Upon determining that the speech input includes instructions for automatically responding to a subsequent incoming communication from one or more specified senders (“Yes” branch), the digital assistant determines (<b>508</b>) whether the instructions include an expiration period for the instructions.

Upon determining that the instructions include an expiration period for the instructions (“Yes” branch), the digital assistant stores (<b>510</b>) the expiration period. For example, instructions module <b>352</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) stores the expiration period for the instructions in a memory included in or separate from instructions module <b>352</b>.

After storing the expiration period (“Yes” branch) or upon determining that the instructions do not include an expiration period for the instructions (“No” branch), the digital assistant determines (<b>512</b>) whether the instructions include a condition precedent to performance of the specified action.

Upon determining that the instructions include a condition precedent (“Yes” branch), the digital assistant stores (<b>514</b>) the condition precedent. For example, instructions module <b>352</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) stores the condition precedent in a memory included in or separate from instructions module <b>352</b>.

After storing the condition precedent (“Yes” branch) or upon determining that the instructions do not include a condition precedent (“No” branch), the digital assistant determines (<b>516</b>) whether the instructions included in the received speech input are complete (i.e., the instructions include enough details or information to perform the specified action).

Upon determining that the instructions are incomplete (“No” branch), auto response module <b>350</b> causes (<b>518</b>) dialogue processing module <b>340</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) to initiate a dialogue with the user to gather complete details or instructions in order to perform the specified action. For example, the user asks the DA, “If Tony calls, email him movie times.” In this example, the user has failed to indicate a specific movie title and a day or time range(s) for showtimes. In this case, auto response module <b>350</b> causes dialogue processing module <b>340</b> to initiate a dialogue with the user to determine the movie title and the day for which the user wants to send Tony showtimes.

Upon determining that the instructions are complete (“Yes” branch), the digital assistant stores (<b>520</b>) the instructions at least including the one or more specified senders and the specified action. For example, instructions module <b>352</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) stores the one or more specified senders and the specified action in a memory included in or separate from instructions module <b>352</b>.

<figref idref="DRAWINGS">FIG. <b>6</b></figref> illustrates a flow diagram of a method <b>600</b> of operating a digital assistant in accordance with some embodiments. In some embodiments, method <b>600</b> is performed at an electronic device including one or more processors and memory (e.g., a respective DA-client <b>102</b> or DA-server <b>106</b>, <figref idref="DRAWINGS">FIG. <b>1</b></figref>). In some embodiments, method <b>600</b> is performed at digital assistant <b>326</b> illustrated in <figref idref="DRAWINGS">FIGS. <b>3</b>A-<b>3</b>B</figref>. In some embodiments, method <b>600</b> is governed by a set of instructions stored in memory (e.g., a non-transitory computer readable storage medium) that are executed by the one or more processors of the electronic device.

Subsequent to storing instructions for automatically responding to a subsequent incoming communication from one or more specified senders, the electronic device (e.g., user device <b>104</b>, <figref idref="DRAWINGS">FIG. <b>1</b></figref>) receives (<b>602</b>) an incoming communication from a respective sender. For example, the incoming communication is one of an email, phone call, video call, VoIP call, SMS or text message, MMS, voice message, and the like.

The digital assistant determines (<b>604</b>) whether the instructions for automatically responding to a subsequent incoming communication from one or more specified senders are triggered. Auto response module <b>350</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) or a component thereof (e.g., determination module <b>354</b>, <figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) determines whether the respective sender is one of the one or more specified senders included in the instructions. As discussed above, there are a plurality of procedures for determining whether the respective sender of the subsequent incoming communication is one of the one or more specified senders. In some embodiments, auto response module <b>350</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) or a component thereof (e.g., determination module <b>354</b>, <figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) also determines whether the incoming communication is of a communication type specified by the instructions.

Upon determining that the instructions for automatically responding to a subsequent incoming communication from one or more specified senders are triggered, method <b>600</b> follows the “Yes” branch to step <b>612</b> (or, one of steps <b>606</b> or <b>608</b> if the instructions include an expiration period and/or condition precedent, or, in some embodiments, step <b>610</b>). For example, the respective sender is one of the one or more specified senders, and, in some cases, the incoming communication utilizes one of the one or more specified communication types. Upon determining that the instructions for automatically responding to a subsequent incoming communication from one or more specified senders are not triggered, method <b>600</b> follows the “No” branch to step <b>602</b> to receive another incoming communication and repeat the determination process.

In some embodiments, when the instructions include an expiration period, the digital assistant or a component thereof (e.g., determination module <b>354</b>, <figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) determines (<b>606</b>) whether the expiration period has elapsed. Upon determining that the expiration period has elapsed prior to receiving the incoming communication, method <b>600</b> follows the “Yes” branch to step <b>614</b> and auto response module <b>350</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) or a component thereof (e.g., instructions module <b>352</b>, <figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) automatically deletes the instructions. Upon determining that the expiration period has not elapsed prior to receiving the incoming communication, method <b>600</b> follows the “No” branch to step <b>612</b> (or, in some embodiments, step <b>608</b> or <b>610</b>).

In some embodiments, when the instructions include a condition precedent to performance of the specified action, the digital assistant or a component thereof (e.g., determination module <b>354</b>, <figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) determines (<b>608</b>) whether the condition precedent has been satisfied. Upon determining that the condition precedent has not been satisfied prior to or concurrent with receiving the incoming communication, method <b>600</b> follows the “No” branch to step <b>602</b> to receive another incoming communication and repeat the determination process. Upon determining that the condition precedent has been satisfied prior to or concurrent with receiving the incoming communication, method <b>600</b> follows the “Yes” branch to step <b>612</b> (or, in some embodiments, step <b>610</b>).

In some embodiments, the digital assistant or a component thereof (e.g., composition module <b>356</b>, <figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) composes (<b>610</b>) a customized response to the respective sender. The customized response is composed in accordance with the details or information included in the instructions and, optionally, is based on context information associated with the user of user device <b>104</b>, <figref idref="DRAWINGS">FIG. <b>1</b></figref> (e.g., location, pattern or behavior information or a calendar or schedule associated with the user). For example, the user asks the digital assistant, “If Swapnil tries to contact me, let him know I'm in a meeting and propose a meeting during a time that I'm available this afternoon” In this example, after determining that a subsequent incoming communication is received from Swapnil (e.g., based on the address book associated with the user), the digital assistant composes a message to Swapnil stating, “I'm in a meeting right let's meet at 4 PM to discuss client matters” and sends a calendar invite to Swapnil for 4 PM this afternoon. In this example, the DA composes the message to Swapnil at least in part on the user's calendar or schedule for the day (e.g., context information).

Upon determining that the instructions for automatically responding to a subsequent incoming communication from one or more specified senders are triggered, the digital assistant performs (<b>612</b>) the specified action. For example, auto response module <b>350</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) or a component thereof (e.g., performance module <b>358</b>, <figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) sends the customized response (e.g., composed by composition module <b>356</b>, <figref idref="DRAWINGS">FIG. <b>3</b>A</figref> in step <b>610</b>) to the respective user via one of a plurality of communication means. In some embodiments, performance module uses the same means of communication to send the customized response as was used for the incoming communication. For example, the specified action includes sending one of an email, phone call, video call, VoIP call, SMS or text message, MMS, voice message, or the like to the specified sender.

In some embodiments, performance module is configured to perform the specified action without further review or instruction from the user. In some embodiments, performing the specified action includes performing a first sub-action and performing a second sub-action. For example, a user asks the DA, “If my wife calls, tell her to meet me at Cyrano's Restaurant tonight and, also, send her a calendar invite for 7 PM entitled ‘Date Night’ 30 minutes after sending the text.” In this example, in response to receiving an incoming phone call from the user's wife, performance module <b>358</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) is configured to perform the first sub-action included in the instructions (e.g., sending a text message to the user's wife stating “Meet me at Cyrano's tonight.”). And, further in this example, performance module <b>358</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) is also configured to perform the second sub-action included in the instructions 30 minutes after sending the text message to the user's wife (e.g., sending a calendar invite to the user's wife entitled ‘Date Night’ for 7 PM that evening).

In one example, auto response module <b>350</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) responds to an incoming phone call from a specified sender by sending a voice message to the specified sender including a recording of the user's voice from the speech input including the instructions or a speech input recorded prior to receiving the instructions. In another example, auto response module <b>350</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) responds to an incoming communication call from a specified sender by sending a voice message to the specified sender that is a digitized or text-to-speech version of a text input from the user.

After performing the specified action, the electronic device automatically deletes (<b>614</b>) the instructions. For example, auto response module <b>350</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) or a component thereof (e.g., instructions module <b>352</b>, <figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) deletes the instructions stored in the memory included in or separate from instructions module <b>352</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>). In some embodiments, instructions module <b>352</b> (<figref idref="DRAWINGS">FIG. <b>3</b>A</figref>) automatically deletes an expiration period and/or condition precedent in addition to the one or more specified senders and the specified action included in the instructions.

It should be understood that the particular order in which the operations in <figref idref="DRAWINGS">FIGS. <b>5</b>-<b>6</b></figref> have been described is merely exemplary and is not intended to indicate that the described order is the only order in which the operations could be performed. One of ordinary skill in the art would recognize various ways to reorder the operations described herein.

In accordance with some embodiments, <figref idref="DRAWINGS">FIG. <b>7</b></figref> shows a functional block diagram of an electronic device <b>700</b> configured in accordance with the principles of the various described embodiments. The functional blocks of the device are, optionally, implemented by hardware, software, or a combination of hardware and software to carry out the principles of the various described embodiments. It is understood by persons of skill in the art that the functional blocks described in <figref idref="DRAWINGS">FIG. <b>7</b></figref> are, optionally, combined or separated into sub-blocks to implement the principles of the various described embodiments. Therefore, the description herein optionally supports any possible combination or separation or further definition of the functional blocks described herein.

As shown in <figref idref="DRAWINGS">FIG. <b>7</b></figref>, electronic device <b>700</b> includes a sound receiving unit <b>702</b> configured to obtain a speech input from a user. In some embodiments, electronic device <b>700</b>, optionally, includes a speaker unit <b>704</b> configured to generate sound and a touch screen display unit <b>706</b> configured to display information and to receive one or more touch inputs. Electronic device <b>700</b> also includes a processing unit <b>708</b> coupled to sound receiving unit <b>702</b> (and, optionally, coupled to speaker unit <b>704</b> and touch screen display unit <b>706</b>). In some embodiments, processing unit <b>708</b> includes an instructions determination unit <b>710</b>, a storing unit <b>712</b>, an communications obtention unit <b>714</b>, a sender ascertainment unit <b>716</b>, a performing unit <b>718</b>, a deleting unit <b>720</b>, a communication type determination unit <b>722</b>, a converting unit <b>724</b>, and a composing unit <b>726</b>.

Processing unit <b>708</b> is configured to: in response to obtaining the speech input, determine (e.g., with instructions determination unit <b>710</b>) whether the speech input includes instructions for performing a specified action in response to receipt of a subsequent incoming communication from one or more specified senders; and store (e.g., with storing unit <b>712</b>) the instructions. Processing unit <b>708</b> is also configured to: after storing the instructions, obtain (e.g., with communications obtention unit <b>714</b>) an incoming communication from a respective sender; and determine (e.g., with sender ascertainment unit <b>716</b>) whether the respective sender is one of the one or more specified senders. Processing unit <b>708</b> is further configured to perform (e.g., with performing unit <b>718</b>) the specified action in accordance with the instructions upon determining that the respective sender is one of the one or more specified senders and thereafter automatically delete (e.g., with deleting unit <b>720</b>) the instructions.

In some embodiments, determining whether the speech input includes instructions includes determining (e.g., with instructions determination unit <b>710</b>) whether the speech input includes instructions for performing a specified action in response to receipt of one or more specified subsequent incoming communication types from one or more specified senders; processing unit <b>708</b> is configured to determine (e.g., with communication type determination unit <b>722</b>) whether the incoming communication is one of the one or more specified subsequent incoming communication types; and performing the specified action includes, upon determining that the respective sender is one of the one or more specified senders and that the incoming communication is one of the one or more specified subsequent incoming communication types, performing (e.g., with performing unit <b>718</b>) the specified action in accordance with the instructions and thereafter automatically deleting (e.g., with deleting unit <b>720</b>) the instructions.

In some embodiments, a respective specified subsequent incoming communication type of the one or more specified subsequent incoming communication types is one of a phone call, voice message, voicemail, video call, SMS, MMS, VOIP call, or email.

In some embodiments, the incoming communication is a phone call, and the specified action is sending a voice message.

In some embodiments, at least a part of the voice message is a recording of the user's voice.

In some embodiments, at least a part of the voice message is a digitized or text-to-speech version of input text.

In some embodiments, processing unit <b>708</b> is configured to natural language processing perform (e.g., with converting unit <b>724</b>) on the speech input so as to convert the speech input into text, and where storing the instructions includes storing the instructions as text.

In some embodiments, performing the specified action includes: composing (e.g., with composing unit <b>726</b>) a response to the respective sender in accordance with the instructions; and communicating (e.g., with performing unit <b>718</b>) the response to the sender.

In some embodiments, the communicating is one of a phone call, voicemail, video call, SMS, MMS, VOIP call, or email.

In some embodiments, the communicating uses the same means of communication as the incoming communication.

In some embodiments, the composing includes composing (e.g., with composing unit <b>726</b>) the response to the respective sender in accordance with the instructions and based at least in part on contextual information.

In some embodiments, determining whether the respective sender is one of the one or more specified senders includes ascertaining (e.g., with sender ascertainment unit <b>716</b>) whether the respective sender is one of the one or more specified senders based on a list of contacts associated with the user of the device.

In some embodiments, determining whether the respective sender is one of the one or more specified senders includes ascertaining (e.g., with sender ascertainment unit <b>716</b>) whether the respective sender is one of the one or more specified senders based on caller ID associated with the respective sender.

In some embodiments, processing unit <b>708</b> is configured to identify (e.g., with sender ascertainment unit <b>716</b>) an address associated with the sender of the communication; and determining whether the respective sender is one of the one or more specified senders includes ascertaining (e.g., with sender ascertainment unit <b>716</b>) whether the sender is one of the one or more specified senders based on the address associated with the respective sender of the communication.

In some embodiments, determining whether the respective sender is one of the one or more specified senders includes ascertaining (e.g., with sender ascertainment unit <b>716</b>) whether the sender is one of the one or more specified senders based on the content of the incoming communication received from the respective sender.

In some embodiments, the incoming communication is one of a phone call, voice message, voicemail, video call, SMS, MMS, VOIP call, or email.

In some embodiments, the action is selected from the group consisting of: sending a voice message to the sender; sending an SMS message to the sender; sending an MMS or photograph to the sender; sending an email to the sender; sending an event invite to the sender; sharing one or more calendar entries with the sender; and sharing one or more custom attributes with the sender.

In some embodiments, the performing (e.g., with performing unit <b>718</b>) and deleting (e.g., with deleting unit <b>720</b>) are automatically performed without further review or instruction from the user of electronic device <b>700</b>.

In some embodiments, performing the specified action includes: performing (e.g., with performing unit <b>718</b>) a first sub-action; and performing (e.g., with performing unit <b>718</b>) a second sub-action different from the first sub-action.

In some embodiments, the instructions further specify an expiration period; and processing unit <b>708</b> is configured to automatically delete (e.g., with deleting unit <b>720</b>) the instructions upon determining that the respective sender is not one of the one or more specified senders and that the expiration period has elapsed.

In some embodiments, the respective sender is a first respective sender; and processing unit <b>708</b> is configured to: upon determining that the first respective sender is not one of the one or more specified senders and the expiration period has not elapsed, forgo deletion of the instructions; obtain (e.g., with communications obtention unit <b>714</b>) an incoming communication from a second respective sender different from the first respective sender; determine (e.g., with sender ascertainment unit <b>716</b>) whether the second respective sender is one of the one or more specified senders; and upon determining that the second respective sender is one of the one or more specified senders and that the expiration period has not elapsed, perform (e.g., with performing unit <b>718</b>) the specified action in accordance with the instructions and thereafter automatically deleting the instructions.

The foregoing description, for purpose of explanation, has been described with reference to specific implementations. However, the illustrative discussions above are not intended to be exhaustive or to limit the disclosed implementations to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. The implementations were chosen and described in order to best explain the principles and practical applications of the disclosed ideas, to thereby enable others skilled in the art to best utilize them with various modifications as are suited to the particular use contemplated.

Although the terms “first,” “second,” etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first speech input could be termed a second speech input, and, similarly, a second speech input could be termed a first speech input, without changing the meaning of the description, so long as all occurrences of the “first speech input” are renamed consistently and all occurrences of the “second speech input” are renamed consistently. The first speech input and the second speech input are both speech inputs, but they are not the same speech input.

The terminology used herein is for the purpose of describing particular implementations only and is not intended to be limiting of the claims. As used in the description of the implementations and the appended claims, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and/or” as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. It will be further understood that the terms “comprises” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

As used herein, the term “if” may be construed to mean “when” or “upon” or “in response to determining” or “in accordance with a determination” or “in response to detecting,” that a stated condition precedent is true, depending on the context. Similarly, the phrase “if it is determined [that a stated condition precedent is true]” or “if [a stated condition precedent is true]” or “when [a stated condition precedent is true]” may be construed to mean “upon determining” or “upon a determination that” or “in response to determining” or “in accordance with a determination” or “upon detecting” or “in response to detecting” that the stated condition precedent is true, depending on the context.